Metraipolis › archive › dc_088b75927ea1

SWAP-INR: Implicit Neural Representation with Switchable Attention Paths for Time-varying Multivariate Scientific Data Compression — arXiv:2611.04423

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04423
License (as archived)
CC0-1.0
Archived
2026-11-04T21:52:51.372Z
SHA-256 of the archived text
950bf347cb3f8bee998d3bec079120645c8d878fdbd03369428a99835d63804e
Stable URL of this page
https://metraipolis.com/documento/dc_088b75927ea1

How to cite

SWAP-INR: Implicit Neural Representation with Switchable Attention Paths for Time-varying Multivariate Scientific Data Compression — arXiv:2611.04423 — arXiv (en), https://arxiv.org/abs/2611.04423 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_088b75927ea1 (Metraipolis archive dc_088b75927ea1, sha256 950bf347cb3f8bee998d3bec079120645c8d878fdbd03369428a99835d63804e)
BibTeX
@misc{dc088b75927ea1,
  title = {SWAP-INR: Implicit Neural Representation with Switchable Attention Paths for Time-varying Multivariate Scientific Data Compression — arXiv:2611.04423},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04423},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_088b75927ea1; sha256 950bf347cb3f8bee998d3bec079120645c8d878fdbd03369428a99835d63804e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04423. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visualizing multivariate scientific simulation data is essential for understanding complex physical phenomena, yet the massive scale of such data imposes a severe storage bottleneck in high-performance computing environments. Implicit neural representations (INRs) have emerged as a promising continuous alternative to traditional lossy compressors, but existing methods struggle to explicitly capture cross-variable interactions and to adapt to the diverse spectral characteristics of physical variables. To address these limitations, we propose SWAP-INR, an architecture for high-fidelity compression of multivariate, time-varying simulation data. SWAP-INR introduces two key components: (1) The switchable attention path (SWAP) module explicitly models cross-variable interactions through a cross-variable attention layer, then routes each variable to an attention or non-attention path by a deterministic, loss-driven criterion, and prunes the inactive layers for structural compression. (2) The adaptability amplification SIREN (A2-SIREN) replaces rigid frequency scaling with channel-wise learnable modulation, adapting to heterogeneous physical features with negligible overhead. Combined with post-training 16-bit quantization, SWAP-INR achieves state-of-the-art performance on small modular reactor (SMR) datasets and remains competitive on public physics simulation datasets, while maintaining a constrained memory footprint. Our code is this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.04423 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T21:38:49.812Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).